Target-based Surrogates for Stochastic Optimization
University of British Columbia（不列颠哥伦比亚大学）；Simon Fraser University（西蒙弗雷泽大学）；Samsung - SAIT AI Lab（三星综合技术院人工智能实验室）；Canada CIFAR AI Chair (Amii)（加拿大高等研究院人工智能讲席（阿尔伯塔机器智能研究所））；Microsoft Research（微软研究院）；Canada CIFAR AI Chair (MILA)（加拿大高等研究院人工智能讲席（蒙特利尔学习算法研究所））
Jonathan Wilder Lavington, Sharan Vaswani, Reza Babanezhad, Mark Schmidt, Nicolas Le Roux
We consider minimizing functions for which it is expensive to compute the (possibly stochastic) gradient. Such functions are prevalent in reinforcement learning, imitation learning and adversarial training. Our target optimization framework uses the (expensive) gradient computation to construct surrogate functions in a \emph{target space} (e.g. the logits output by a linear model for classification) that can be minimized efficiently. This allows for multiple parameter updates to the model, amortizing the cost of gradient computation. In the full-batch setting, we prove that our surrogate is a global upper-bound on the loss, and can be (locally) minimized using a black-box optimization algorithm. We prove that the resulting majorization-minimization algorithm ensures convergence to a stationary point of the loss. Next, we instantiate our framework in the stochastic setting and propose the $SSO$ algorithm, which can be viewed as projected stochastic gradient descent in the target space. This connection enables us to prove theoretical guarantees for $SSO$ when minimizing convex functions. Our framework allows the use of standard stochastic optimization algorithms to construct surrogates which can be minimized by any deterministic optimization method. To evaluate our framework, we consider a suite of supervised learning and imitation learning problems. Our experiments indicate the benefits of target optimization and the effectiveness of $SSO$.
Stochastic majorization-minimization (SMM) is a class of stochastic optimization algorithms that proceed by sampling new data points and minimizing a recursive average of surrogate functions of an objective function. The surrogates are required to be strongly convex and convergence rate analysis for the general non-convex setting was not available. In this paper, we propose an extension of SMM where surrogates are allowed to be only weakly convex or block multi-convex, and the averaged surrogates are approximately minimized with proximal regularization or block-minimized within diminishing rad…
Stochastic Gradient Descent (SGD) has played a central role in machine learning. However, it requires a carefully hand-picked stepsize for fast convergence, which is notoriously tedious and time-consuming to tune. Over the last several years, a plethora of adaptive gradient-based algorithms have emerged to ameliorate this problem. They have proved efficient in reducing the labor of tuning in practice, but many of them lack theoretic guarantees even in the convex setting. In this paper, we propose new surrogate losses to cast the problem of learning the optimal stepsizes for the stochastic opti…
Surrogate risk minimization is an ubiquitous paradigm in supervised machine learning, wherein a target problem is solved by minimizing a surrogate loss on a dataset. Surrogate regret bounds, also called excess risk bounds, are a common tool to prove generalization rates for surrogate risk minimization. While surrogate regret bounds have been developed for certain classes of loss functions, such as proper losses, general results are relatively sparse. We provide two general results. The first gives a linear surrogate regret bound for any polyhedral (piecewise-linear and convex) surrogate, meani…
Establishing Linear Surrogate Regret Bounds for Convex Smooth Losses via Convolutional Fenchel-Young Losses
College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院）；The Institute of Statistical Mathematics（统计数学研究所）；School of Computer Science and Engineering, Southeast University（东南大学计算机科学与工程学院）；Skywork AI
We consider optimization of generalized performance metrics for binary classification by means of surrogate losses. We focus on a class of metrics, which are linear-fractional functions of the false positive and false negative rates (examples of which include $F_β$-measure, Jaccard similarity coefficient, AM measure, and many others). Our analysis concerns the following two-step procedure. First, a real-valued function $f$ is learned by minimizing a surrogate loss for binary classification on the training sample. It is assumed that the surrogate loss is a strongly proper composite loss functio…
CMAP, École polytechnique, Insitut Polytechnique de Paris（CMAP，巴黎高等理工学院，巴黎理工 institute）；LAAS-CNRS, Université de Toulouse, CNRS, Toulouse, France（LAAS-CNRS，图卢兹大学，CNRS，法国图卢兹）；Department of SEEM, The Chinese University of Hong Kong Shatin, Hong Kong（信息工程系，香港中文大学（深圳））
Non-Stationary Online Structured Prediction with Surrogate Losses
CyberAgent, Tokyo, Japan（日本东京CyberAgent公司）；National Institute of Informatics, Tokyo, Japan（日本东京信息机构）；Center for Advanced Intelligence Project, RIKEN, Tokyo, Japan（日本东京RIKEN高级智能项目）；The Institute of Statistical Mathematics, Tokyo, Japan（日本东京统计数学研究所）；Tohoku University, Miyagi, Japan（日本宫城县立东大学）；Nanyang Technological University, Singapore（新加坡南洋理工大学）
University of Oxford（牛津大学）；Microsoft Research（微软研究院）
Trust Region Policy Optimization (TRPO) is an iterative method that simultaneously maximizes a surrogate objective and enforces a trust region constraint over consecutive policies in each iteration. The combination of the surrogate objective maximization and the trust region enforcement has been shown to be crucial to guarantee a monotonic policy improvement. However, solving a trust-region-constrained optimization problem can be computationally intensive as it requires many steps of conjugate gradient and a large number of on-policy samples. In this paper, we show that the trust region constr…
INRIA/ENS（法国国家信息与自动化研究所/巴黎高等师范学院）；HSE（高等经济学院）；MILA（米拉魁北克人工智能研究所）；DIRO（计算机科学与运筹学系）；Université de Montréal（蒙特利尔大学）
We provide novel theoretical insights on structured prediction in the context of efficient convex surrogate loss minimization with consistency guarantees. For any task loss, we construct a convex surrogate that can be optimized via stochastic gradient descent and we prove tight bounds on the so-called "calibration function" relating the excess surrogate risk to the actual risk. In contrast to prior related work, we carefully monitor the effect of the exponential number of classes in the learning guarantees as well as on the optimization complexity. As an interesting consequence, we formalize t…
Kuang-Chi Institute of Advanced Technology（光启高等理工研究院）；ZenRhyme Consulting Services（ZenRhyme咨询服务公司）
Stochastic variational inference (SVI) plays a key role in Bayesian deep learning. Recently various divergences have been proposed to design the surrogate loss for variational inference. We present a simple upper bound of the evidence as the surrogate loss. This evidence upper bound (EUBO) equals to the log marginal likelihood plus the KL-divergence between the posterior and the proposal. We show that the proposed EUBO is tighter than previous upper bounds introduced by $χ$-divergence or $α$-divergence. To facilitate scalable inference, we present the numerical approximation of the gradient of…
Cornell University（康奈尔大学）；Uber AI Labs（优步人工智能实验室）；National University of Singapore（新加坡国立大学）
This paper describes Plumbing for Optimization with Asynchronous Parallelism (POAP) and the Python Surrogate Optimization Toolbox (pySOT). POAP is an event-driven framework for building and combining asynchronous optimization strategies, designed for global optimization of expensive functions where concurrent function evaluations are useful. POAP consists of three components: a worker pool capable of function evaluations, strategies to propose evaluations or other actions, and a controller that mediates the interaction between the workers and strategies. pySOT is a collection of synchronous an…
Recent studies have empirically investigated different methods to train stochastic neural networks on a classification task by optimising a PAC-Bayesian bound via stochastic gradient descent. Most of these procedures need to replace the misclassification error with a surrogate loss, leading to a mismatch between the optimisation objective and the actual generalisation bound. The present paper proposes a novel training algorithm that optimises the PAC-Bayesian bound, without relying on any surrogate loss. Empirical results show that this approach outperforms currently available PAC-Bayesian tra…
Goal-oriented learning of stochastic differential equations using error bounds on path-space observables
Center for Computational Science & Engineering, Massachusetts Institute of Technology（麻省理工学院计算科学与工程中心）；Department of Mathematics, University of Potsdam（波茨坦大学数学系）
Skoltech（斯科尔科沃科技学院）；National Research University Higher School of Economics（俄罗斯国立高等经济研究大学）；IITP RAS（俄罗斯科学院信息传输问题研究所）
The key idea of Bayesian optimization is replacing an expensive target function with a cheap surrogate model. By selection of an acquisition function for Bayesian optimization, we trade off between exploration and exploitation. The acquisition function typically depends on the mean and the variance of the surrogate model at a given point. The most common Gaussian process-based surrogate model assumes that the target with fixed parameters is a realization of a Gaussian process. However, often the target function doesn't satisfy this approximation. Here we consider target functions that come fro…
Imperial College London（帝国理工学院）；SLAC National Accelerator Laboratory（SLAC国家加速器实验室）；University of Oxford（牛津大学）
We propose a novel method for gradient-based optimization of black-box simulators using differentiable local surrogate models. In fields such as physics and engineering, many processes are modeled with non-differentiable simulators with intractable likelihoods. Optimization of these forward models is particularly challenging, especially when the simulator is stochastic. To address such cases, we introduce the use of deep generative models to iteratively approximate the simulator in local neighborhoods of the parameter space. We demonstrate that these local surrogates can be used to approximate…
We present a probabilistic deep learning methodology that enables the construction of predictive data-driven surrogates for stochastic systems. Leveraging recent advances in variational inference with implicit distributions, we put forth a statistical inference framework that enables the end-to-end training of surrogate models on paired input-output observations that may be stochastic in nature, originate from different information sources of variable fidelity, or be corrupted by complex noise processes. The resulting surrogates can accommodate high-dimensional inputs and outputs and are able …
We propose a deep learning-based surrogate model for stochastic simulators. The basic idea is to use generative neural network to approximate the stochastic response. The challenge with such a framework resides in designing the network architecture and selecting loss-function suitable for stochastic response. While we utilize a simple feed-forward neural network, we propose to use conditional maximum mean discrepancy (CMMD) as the loss-function. CMMD exploits the property of reproducing kernel Hilbert space and allows capturing discrepancy between the between the target and the neural network …
University of British Columbia（不列颠哥伦比亚大学）；Inverted AI Ltd.（Inverted AI有限公司）；University of Oxford（牛津大学）；Convergent Manufacturing Technologies Inc.（Convergent制造技术公司）；Mila（米拉）
We present a framework for automatically structuring and training fast, approximate, deep neural surrogates of stochastic simulators. Unlike traditional approaches to surrogate modeling, our surrogates retain the interpretable structure and control flow of the reference simulator. Our surrogates target stochastic simulators where the number of random variables itself can be stochastic and potentially unbounded. Our framework further enables an automatic replacement of the reference simulator with the surrogate when undertaking amortized inference. The fidelity and speed of our surrogates allow…
Nanjing University（南京大学）；the University of Iowa（爱荷华大学）
NDCG, namely Normalized Discounted Cumulative Gain, is a widely used ranking metric in information retrieval and machine learning. However, efficient and provable stochastic methods for maximizing NDCG are still lacking, especially for deep models. In this paper, we propose a principled approach to optimize NDCG and its top-$K$ variant. First, we formulate a novel compositional optimization problem for optimizing the NDCG surrogate, and a novel bilevel compositional optimization problem for optimizing the top-$K$ NDCG surrogate. Then, we develop efficient stochastic algorithms with provable co…
Unsupervised domain adaptation (UDA) aims to predict unlabeled data from target domain with access to labeled data from the source domain. In this work, we propose a novel framework called SIDA (Surrogate Mutual Information Maximization Domain Adaptation) with strong theoretical guarantees. To be specific, SIDA implements adaptation by maximizing mutual information (MI) between features. In the framework, a surrogate joint distribution models the underlying joint distribution of the unlabeled target domain. Our theoretical analysis validates SIDA by bounding the expected risk on target domain …
We propose a simple but effective modification of the discriminators, namely measure-conditional discriminators, as a plug-and-play module for different GANs. By taking the generated distributions as part of input so that the target optimum for the discriminator is stationary, the proposed discriminator is more robust than the vanilla one. A variant of the measure-conditional discriminator can also handle multiple target distributions, or act as a surrogate model of statistical distances such as KL divergence with applications to transfer learning.
School of Electrical and Electronic Engineering（电气与电子工程学院）；Institut de Physique Thorique（理论物理研究所）；University of Adelaide（阿德莱德大学）；Bocconi University（博科尼大学）
The training of stochastic neural network models with binary ($\pm1$) weights and activations via continuous surrogate networks is investigated. We derive new surrogates using a novel derivation based on writing the stochastic neural network as a Markov chain. This derivation also encompasses existing variants of the surrogates presented in the literature. Following this, we theoretically study the surrogates at initialisation. We derive, using mean field theory, a set of scalar equations describing how input signals propagate through the randomly initialised networks. The equations reveal whe…
A Simple Approximate Bayesian Inference Neural Surrogate for Stochastic Petri Net Models
School of Computing and Augmented Intelligence, Arizona State University（计算与增强智能学院，亚利桑那州立大学）；School of Mathematical and Statistical Sciences, Arizona State University（数学与统计科学学院，亚利桑那州立大学）；School of Life Sciences, Arizona State University（生命科学学院，亚利桑那州立大学）
Contextual Scenario Generation for Two-Stage Stochastic Programming
Department of Mechanical and Industrial Engineering, University of Toronto（机械与工业工程系，多伦多大学）；Department of Industrial and Systems Engineering, Korea Advanced Institute of Science and Technology (KAIST)（工业与系统工程系，韩国科学技术院（KAIST））
ST Engineering Electronics-SUTD Cyber Security Laboratory（新科工程电子-新加坡科技设计大学网络安全实验室）；Singapore University of Technology and Design（新加坡科技设计大学）；Ben-Gurion University of the Negev（本-古里安大学）；Deutsche Telekom Innovation Laboratories at Ben-Gurion University of the Negev（本-古里安大学德国电信创新实验室）
We investigate to what extent alternative variants of Artificial Neural Networks (ANNs) are susceptible to adversarial attacks. We analyse the adversarial robustness of conventional, stochastic ANNs and Spiking Neural Networks (SNNs) in the raw image space, across three different datasets. Our experiments reveal that stochastic ANN variants are almost equally as susceptible as conventional ANNs when faced with simple iterative gradient-based attacks in the white-box setting. However we observe, that in black-box settings, stochastic ANNs are more robust than conventional ANNs, when faced with …
Low-rank surrogate modeling and stochastic zero-order optimization for training of neural networks with black-box layers
Artificial Intelligence Research Institute (AIRI)（人工智能研究 institute）；Skolkovo Institute of Science and Technology（斯克尔科沃科学与技术研究所）；Sber Quantum Technology Center（Sber 量子技术中心）
ITMO University（圣彼得堡国立信息技术机械与光学大学）；Almazov National Medical Research Center（阿尔马佐夫国家医学研究中心）
The paper proposes and investigates an approach for surrogate-assisted performance prediction of data-driven knowledge discovery algorithms. The approach is based on the identification of surrogate models for prediction of the target algorithm's quality and performance. The proposed approach was implemented and investigated as applied to an evolutionary algorithm for discovering clusters of interpretable clinical pathways in electronic health records of patients with acute coronary syndrome. Several clustering metrics and execution time were used as the target quality and performance metrics r…
University of Alberta（阿尔伯塔大学）；Alberta Machine Intelligence Institute (Amii)（阿尔伯塔机器智能研究院）
One major barrier to applications of deep Reinforcement Learning (RL) both inside and outside of games is the lack of explainability. In this paper, we describe a lightweight and effective method to derive explanations for deep RL agents, which we evaluate in the Atari domain. Our method relies on a transformation of the pixel-based input of the RL agent to an interpretable, percept-like input representation. We then train a surrogate model, which is itself interpretable, to replicate the behavior of the target, deep RL agent. Our experiments demonstrate that we can learn an effective surrogat…
Graz University of Technology（格拉茨工业大学）；Graz Center for Computational Engineering（格拉茨计算工程中心）；University Medicine Essen（埃森大学医学院）；Norwegian University of Science and Technology (NTNU)（挪威科技大学）
Inhomogeneities in the aortic wall can lead to localized stress accumulations, possibly initiating dissection. In many cases, a dissection results from pathological changes such as fragmentation or loss of elastic fibers. But it has been shown that even the healthy aortic wall has an inherent heterogeneous microstructure. Some parts of the aorta are particularly susceptible to the development of inhomogeneities due to pathological changes, however, the distribution in the aortic wall and the spatial extent, such as size, shape, and type, are difficult to predict. Motivated by this observation,…
Inferential Evaluation of Surrogate-Derived Models under Covariate Shift
National University of Singapore（新加坡国立大学）；Peking University Health Science Center, Peking University（北京大学医学部，北京大学）；Beijing International Center for Mathematical Research, Peking University（北京大学北京国际数学研究中心）
We propose a novel training method based on nonlinear multilevel minimization techniques, commonly used for solving discretized large scale partial differential equations. Our multilevel training method constructs a multilevel hierarchy by reducing the number of samples. The training of the original model is then enhanced by internally training surrogate models constructed with fewer samples. We construct the surrogate models using first-order consistency approach. This gives rise to surrogate models, whose gradients are stochastic estimators of the full gradient, but with reduced variance com…
Hyperparameter optimization is the process of identifying the appropriate hyperparameter configuration of a given machine learning model with regard to a given learning task. For smaller data sets, an exhaustive search is possible; However, when the data size and model complexity increase, the number of configuration evaluations becomes the main computational bottleneck. A promising paradigm for tackling this type of problem is surrogate-based optimization. The main idea underlying this paradigm considers an incrementally updated model of the relation between the hyperparameter space and the o…
Indian Institute of Technology (IIT) Delhi（印度理工学院德里分校）
We propose a novel gray-box modeling algorithm for physical systems governed by stochastic differential equations (SDE). The proposed approach, referred to as the Deep Physics Corrector (DPC), blends approximate physics represented in terms of SDE with deep neural network (DNN). The primary idea here is to exploit DNN to model the missing physics. We hypothesize that combining incomplete physics with data will make the model interpretable and allow better generalization. The primary bottleneck associated with training surrogate models for stochastic simulators is often associated with selectin…
